Evaluating and Optimising Models of Network Growth

TL;DR

This paper introduces FETA, a statistically rigorous framework for measuring and optimizing probabilistic models of network growth, applicable across various evolving network types for prediction and simulation.

Contribution

It presents a novel, data-driven method for evaluating and optimizing models of network evolution, enabling accurate simulation and future growth prediction.

Findings

Models accurately reflect real network growth patterns

Artificial topologies match original statistical properties

Framework applicable to diverse network types

Abstract

This paper presents a statistically sound method for measuring the accuracy with which a probabilistic model reflects the growth of a network, and a method for optimising parameters in such a model. The technique is data-driven, and can be used for the modeling and simulation of any kind of evolving network. The overall framework, a Framework for Evolving Topology Analysis (FETA), is tested on data sets collected from the Internet AS-level topology, social networking websites and a co-authorship network. Statistical models of the growth of these networks are produced and tested using a likelihood-based method. The models are then used to generate artificial topologies with the same statistical properties as the originals. This work can be used to predict future growth patterns for a known network, or to generate artificial models of graph topology evolution for simulation purposes. Particular application examples include strategic network planning, user profiling in social networks or infrastructure deployment in managed overlay-based services.